Landmark recognition system and process

Claim 2

A landmark recognition system for autonomous vehicle navigation, characterized by: sensing means (60) for acquiring images; and processing means (12,114,116), connected to said sensing means, for processing the images, computing models, matching models, mapping landmarks, verifying matching, accumulating evidence and determining site uncertainty.

Claim 3

System according to claim 1, characterized by said processing means comprising: image processing means (114), connected to said sensing means (60), for providing features of the landmarks in the acquired images; retrieving means (12) for retrieving models of landmarks; generating means (116), connected to said image processing means and to said retrieving means, for generating expectations about landmarks in the images acquired by said sensing means; matching means (36), connected to said generating means and to said sensing means, for matching images of landmarks according to the features with models of landmarks from a landmark data base; accumulating means (36), connected to said matching means and to said image processing means, for accumulating evidence that indicates a matching confidence of a relevant model of a landmark to an image of a landmark; determining means (72), connected to said image processing means and to said accumulating means, for determining site uncertainty of landmarks located in respective region segments of a geographical area; and storing means, connected to said determining means, for storing site uncertainty information into a data base for the area.

Claim 4

System according to claim 1, characterized by said processing means, comprising: extraction means (114), connected to said sensing means, for extracting objects in the images and extracting features of the objects resulting in an image model; generating means (12) for generating dynamic 2-D models of objects; matching means (116), connected to said extraction means and to said generating means, for dynamic model matching of the 2-D models with the image model, thereby outputting a map location uncertainty; model data base connected to said generating means; map data base (14) connected to said generating means; sensing means model (76) connected to said generating means; and vehicle data base (38) connected to said generating means.

Claim 5

System according to claim 1, characterized by said processing means comprising: a first processor (114), connected to said camera, for processing the images into an image model having segmented regions, extracted objects and features; a second processor (12), connected to said first processor, for outputting expected site models for each of the extracted objects; a third processor (116), connected to said first and second processors, for matching expected site models and features from said second processor to extracted objects and features from said first processor, for accruing evidence of the matching, determining site uncertainty of the models, and for checking consistency between approximated range and sizes of the objects resulting in updated ranges of the objects; a first data base (14), connected to said second processor, having model information, map information and camera information; and a second data base (16), connected to said second and third processors, having current map location, speed and direction of the vehicle, and an updated estimated range and azimuth of the vehicle.

Claim 6

System according to claim 4, characterized in that said second processor (12) comprises: an expected map site and objects reasoner (22) connected to said first and second storage means (14,16); and dynamic expectation models generator (56) connected to said first and third processors (114,116), to said first and second storage means, and to said expected map site and objects reasoner (22).

Claim 7

System according to claim 5, characterized in that said first processor (114) comprises: a low-level processing unit (82) connected to said camera (60); a mid-level processing unit (86) connected to said low-level processing unit (82); a blackboard (84). connected to said mid-level processing unit (86) and to said third processor (116). for structuring information from said mid-level processor and said third processor, and for storing image information: and an image model unit (46), connected to said blackboard (84), and to said second and third processors (12.116), for providing a mechanism for observing the results of the system

Claim 8

A landmark recognition process for autonomous vehicle navigation, characterized by sensing images from a perspective of a vehicle: retrieving models of landmarks: generating expectations about landmarks being in the images; matching images of landmarks with models of landmarks: accumulating evidence that results in a matching confidence of a relevant landmark model to a particular landmark image at a site of the vehicle: determining site uncertainty of landmarks located in respective region segments of a map; and storing site uncertainty information into a knowledge base of the map.

Claim 9

A landmark recognition process for autonomous vehicle navigation, characterized by sensing images from a perspective of a vehicle: retrieving models of landmarks: generating expectations about landmarks being in the images; matching images of landmarks with models of landmarks: accumulating evidence that results in a matching confidence of a relevant landmark model to a particular landmark image at a site of the vehicle: determining site uncertainty of landmarks located in respective region segments of a map; and storing site uncertainty information into a knowledge base of the map.